Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 27-RESID-POST-AA
    6. 131004
    Prev
    Next
    INDEX
    Explanations

    5

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﰁ
    -0.08
    쿵
    -0.08
    ꂫ
    -0.07
    ln
    -0.07
    .add
    -0.07
    爱尔兰
    -0.06
    "The
    -0.06
     bj
    -0.06
     appears
    -0.06
    뽀
    -0.06
    POSITIVE LOGITS
     Prague
    0.08
    heits
    0.08
     Sequelize
    0.07
     IMAGES
    0.07
    	Route
    0.07
    <Guid
    0.07
    uting
    0.07
    �
    0.07
    (enemy
    0.07
     initially
    0.07
    Activations Density 0.010%

    No Known Activations